Earshot is a toolkit that lets AI coding agents analyse and describe audio, check how well sound fits a description or a video, and create their own sound effects in code. It runs locally on a CPU as a command-line tool, a Python library or an MCP server.
synapse
by dinglebear-ai
Synapse is a Rust server and command-line tool that lets AI assistants, or you directly, manage Docker containers, Compose projects, remote hosts over SSH, logs, ZFS storage and files. It is aimed at people running their own servers or home labs who want controlled, audited access from an AI client.
Proof level: ReadWorth a lookAGPL-3.0
No demo yet
Proof level: Read. We read its README and licence and ran our automatic checks. We have not run it yet. So this page is based on its README and our automatic checks.
The catch
Check this first: Very new project with only 2 stars.
Things to check
- Very new project with only 2 stars
- AGPL-3.0 licence has obligations if you offer it as a network service
- Gives an AI access to SSH, Docker and file operations, so it needs careful allowlists and token setup
- Some features are only partly available over REST (14 of 59 actions) and the README lists known parity gaps
Can you use synapse commercially?
Free to use. Anything you distribute that includes it must be open-sourced under the same licence. Running it as an online service also counts, so a hosted version must offer its source.
Not legal advice. Read the project's licence file before building a product on it.
Did it work for you?
One answer per person for each tool a day, with no account and no cookies. Your answer is remembered in this browser only. How we count
What can you do with synapse?
- Ask an AI assistant to list, inspect and manage Docker containers and Compose projects on your servers
- Read logs, check ZFS pools and inspect hosts over SSH from one command-line tool
- Run allowlisted commands and transfer files between hosts with confirmation required for destructive actions
How do you get synapse running?
Install with npm (npx -y @dinglebear/synapse mcp) which downloads a binary from GitHub Releases, build from source with Cargo, or use the Docker image, then add it to your MCP client configuration.
Follow the official instructions in the project README.
Add it to Claude Code
claude mcp add synapse -- npx -y @dinglebear/synapse
From the official MCP Registry (ai.dinglebear/synapse). Only connect MCP servers you trust: they can act on your behalf.
Make money with it
A freelancer could offer managed home-lab or small-server upkeep to clients, using Synapse to speed up monitoring and routine Docker tasks.
An idea, not financial advice. Check the licence before charging for anything built on it.
Ways a business could use it
- Let an AI assistant do routine checks on a small company's Docker servers, such as container status and logs, to cut down on manual admin time
- Offer a freelance server-maintenance service using one tool to inspect hosts and review logs across several client machines
Checked 10 Nov 2026. Summary drafted by AI from the project's README. Proof level 1 of 4, Read: we read its readme and licence and ran our automatic checks. we have not run it yet.
Similar tools in MCP servers
Kanzo is a small kanban board that runs in your browser and also works as an MCP server, so you and your AI coding agents share the same task list. All data sits in one local folder, which can be synced between machines through a private git repository.
A collection of 77 unofficial MCP servers that let AI assistants search and read Iranian websites such as Digikala, Torob, Divar, Snappfood and Alibaba. It is for comparing prices in Toman, finding jobs, cars, travel, laws and market data from Claude, Cursor or any MCP client.